Note: Most Internet Explorer 8 users encounter issues playing the presentation videos. Please update your browser or use a different one if available.

Use of the NAO Robot to Train Kids with Autism Spectrum Disorders

Saturday, 4 May 2013: 09:00-13:00
Banquet Hall (Kursaal Centre)
11:00
Y. WANG1, X. LI1, Y. Zhao2 and C. Wang3, (1)National Key Lab. of Cognitive Neuroscience and Learning, Beijing Normal University, Beijing, China, (2)Institute of Electronic Engineering, Yan Shan University, Qinhuangdao, China, (3)Center for Behavioural Science, School of Medicine, Nankai University, Tianjin, China
Background:

Rapid progress in robotics offers tremendous possibilities for innovation in training for individuals with ASDs. Humanoid robots show potential in this regard because they are predictable, simple and easy to comprehend (Nadel, 2004) and they can be designed in accordance of the particular interests and comprehension deficits of children with ASDs. However, the efficacy and effectiveness research on this topic is in its infancy.

Objectives:  

The objective of this study is to investigate how a humanoid robot NAO (Aldebaran-Robotics) can, by appearing more predictable, appealing and simple than a human being, facilitate social interaction skills of kids with ASDs over a period of several months.

Methods:  

Four children with ASDs age 5-10 from special education unit at Small World School in Tianjin, China, were selected to participate in the investigation. The NAO robot was connected to a laptop and placed on the floor in a quiet and light room at school. One investigator controlled the laptop in a remote area when necessary and another investigator or teacher was sitting in the room just in case the child needed help. Each trial lasted as long as the child was comfortable with staying in the room. The cameras operated by a remote control. Each child participated in as many trials as possible during a period of four months, with an average of thirty-two trials each. The trials were designed to progressively move from very simple exposure to the robot to more complex opportunities for interaction, such as, eye-gazing, touching, waving hands, repeating, imitating, etc.

Results:  

Based on the video material documenting the interactions, a quantitative and qualitative analysis was conducted. Some elementary behaviour criteria (such as eye-gaze, touch, pointing, social smile, attending to sounds, following instructions, etc.) were defined in our trials that were evaluated throughout the period of trials. The four children with ASDs all showed improvement in their social interaction skills after the trails for four months based on the frequency and duration of the basic behaviours, for instance, they tended to help NAO when he fell over, but had no response when it happened on human beings. The children realized when they made a mistake in imitation and corrected themselves. In some cases, the children used the robot as a mediator, an object of shared attention, for their interaction with other human beings.

Conclusions:  

This study presented a longitudinal investigation on the exposure of children with ASDs to a humanoid robot. The findings clearly demonstrate the need for, and benefits of, long-term studies in order to reveal the full potential of humanoid robots in the therapy and education of children with ASDs.

| More